On this page, you can download the workshop proposal as well as all accepted position papers for HCXAI'25.

The proceedings of all accepted workshop papers can be downloaded here
Also see the collection at: https://zenodo.org/records/15104919 

At HCXAI, we like to do things differently... 

Rather than traditional keynotes or one-way monologues, we have a tradition of having a MAIN EVENT where thought leaders join us for an exciting, engaging, and interactive conversation. The event has a fireside chat vibe where thoughtful discussions take place.  This is not your typical panel; it is a space for dialogue, where the audience is a vital part of the conversation.

This year’s event, “Who Speaks, Who Listens: The Dialogues We Need in Explainable AI,” brings together a star-studded lineup across sectors to confront some of the most urgent and timely questions in XAI. 

Speaker Bios:
Dr. Mary L. Gray is Senior Principal Researcher at Microsoft Research and Faculty Associate at Harvard University’s Berkman Klein Center for Internet and Society. She maintains a faculty position in the Luddy School of Informatics, Computing, and Engineering with affiliations in Anthropology and Gender Studies at Indiana University. Mary, an anthropologist and media scholar by training, focuses on how people’s everyday uses of technologies transform labor, identity, and human rights. Mary earned her PhD in Communication from the University of California at San Diego in 2004, under the direction of Susan Leigh Star. In 2020, Mary was named a MacArthur Fellow for her contributions to anthropology and the study of technology, digital economies, and society.

Dr. Maryam Ashoori is the Senior Director of Product Management and Head of Product for IBM's watsonx.ai, where she spearheads the product strategy and delivery of IBM's watsonx Foundation Models. With over 15 years of experience building data-driven technologies, she has a strong track record of creating high-impact products that both drive demand and delight users. Her leadership spans engineering, design, science, and product management, resulting in diverse, high-performing teams whose work has reached millions globally. Previously, she served as Head of Engineering for Lyft Bikes and Scooters Operations, and spent six years at IBM Research designing user experiences for emerging AI and quantum technologies. She holds a Ph.D. in System Design Engineering from the University of Waterloo, two Master’s degrees in Artificial Intelligence, and currently serves as an Adjunct Professor at Waterloo.

Dr. Jacob Metcalf leads Data & Society’s AI on the Ground program, which uses social science to analyze how AI systems shape power, governance, and accountability. His work centers on how impacted communities can assert influence over the design and evaluation of AI. He studies participatory assessments, red-teaming, algorithmic audits (e.g., NYC’s Local Law 144), and legal recourse for AI harms. Jake co-founded the Algorithmic Impact Methods Lab, co-leads the NSF-funded CLIMATE Hub, and frequently advises policymakers on AI regulation. His recent projects explore AI procurement in local governments and the entanglements between AI, climate, and wildfires in California. 

09:30am: Main Event
10:40am: Session #1 Civic AI and the Global South

• Towards Explainable AI for Government Workers Norma Elva Chavez and Jose Emilio Garcia. 
• Explanations for Trustworthy AI in Critical Infrastructure: A Case from Wastewater Treatment in Norway Asbjørn Følstad, Sølve Eidnes and Hilde Johansen.
• Culturally Attuned Explainable AI: Developing a Research Agenda for Globally Inclusive AI Systems Liliana Savage Pinto.
• Explainable AI through the lens of Legitimate AI Jasper van der Waa and Marissa Hoekstra. 

11:25am: Session #2 LLMs and Explainability
 

• Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines Ramesh Manuvinakurike, Emanuel Moss, Elizabeth Watkins, Saurav Sahay, Giuseppe Raffa and Lama Nachman. 
• Mitigating LLM Hallucinations with Knowledge Graphs: A Case Study Harry Li, Gabriel Appleby, Kenneth Alperin, Steven R Gomez and Ashley Suh.
• Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations Ashley Suh, Kenneth Alperin, Harry Li and Steven R Gomez. 
• Explainable AI in Usable Privacy and Security: Challenges and Opportunities Vincent Freiberger, Arthur Fleig and Erik Buchmann.

12:00am: Lunch Break
01:30pm: Session #3: Responsible Practices

• Legally-Informed Explainable AI Gennie Mansi, Naveena Karusala and Mark Rield.
• Algorithmic Mirror: Designing an Interactive Tool to Promote Self-Reflection for YouTube Recommendations Yui Kondo, Kevin Dunnell, Qing Xiao, Jun Zhao and Luc Rocher.
• “Help me to understand explainable AI “: ExUI – an Explanation Interface to evaluate user-centered XAI Anne Schwerk, Hady Emami and Lothar Blum. 
• Towards Responsible AI: XAI as a Catalyst for Participatory Development Practices Emma Kallina and Jatinder Singh. 

02:15pm: Session #4: XAI Designs and Applications

• Expanding HCXAI in the Age of AI Agents: Challenges and Recommendations Andrea Ferrario. 
• The Importance of Explainable AI for Gig Workers: A Case for Human-Centered XAI in the Gig Economy Kashif Imteyaz and Saul Saul Lopez.
• XAI meets Data-Centric AI: The Need to Explain Data Processing Nadja Geisler and Carsten Binnig.
• Exploration of Temporal Aspects of AI Explanations Ambika Shahu, Nori Greinecker, Dacia Braca, Nina Hubig and Philipp Wintersberger.

03:00pm: Group Work
04:45pm: Wrap-Up and Closing

📢BREAKING: Based on popular demand, you can attend the Human-centered Explainable AI (#HCXAI) workshop at #CHI2025 without an accepted paper! Please repost and help us spread the word.

💡Spots are extremely limited so fill this form out ASAP 

Why are we opening things up?

💡Over the last 5 years, practitioners & policymakers have shared challenges of submitting a paper (bandwidth, resources, etc.). So, we reduced barriers to entry 🎁

✨ Over 400+ top-notch thinkers from 19 countries and 9 sectors have joined us since 2021.  Be part of the next cohort! 

Explainable AI (XAI) is more than just “opening” the black box — who opens it matters just as much, if not more, as the ways of opening it. Human-centered XAI (HCXAI) advocates that algorithmic transparency alone is not sufficient for making AI explainable. In our fifth CHI workshop on Human-Centered XAI (HCXAI), we shift our focus to new, emerging frontiers of explainability: (1) participatory approaches toward explainability in civic AI applications; (2) addressing hallucinations in LLMs using explainability benchmarks; (3) connecting HCXAI research with Responsible AI practices, algorithmic auditing, and public policy; and (4) improving representation of XAI issues from the Global South. We have built a strong community of HCXAI researchers through our workshop series whose work has made important conceptual, methodological, and technical impact on the field. In this installment, we will push the frontiers of work in HCXAI with an emphasis on operationalizing perspectives sociotechnically.

Read the HCXAI 2025 workshop proposal by clicking here. 

Explainable AI(XAI) is an essential pillar of Responsible AI. Explanations can improve real-world efficacy, provide harm mitigation levers, and serve as a primary means to ensure humans’ right to understand and contest decisions made about them by AI systems. This workshop serves as a junction point of cross-disciplinary stakeholders of the XAI landscape
to examine how human-centered perspectives in XAI can be operationalized at the conceptual, methodological, and technical levels. We call for position or empirical papers making justifiable arguments that address topics involving the who (e.g., relevant diverse stakeholders), why (e.g., social/individual factors influencing explainability goals), when (e.g., when to trust the AI’s explanations vs. not) or where (e.g., diverse application areas, XAI for actionability or human-AI collaboration, or XAI evaluation).
In the fifth Human-centered XAI workshop, there is a special focus on emerging frontiers of XAI: (1) participatory approaches toward explainability in civic AI applications; (2) addressing hallucinations in LLMs using explainability benchmarks; (3) connecting HCXAI research with Responsible AI practices, algorithmic auditing, and public policy; and (4) improving representation of XAI issues from the Global South. Reviews are author-disclosed (single-blind). All accepted papers will be presented, provided at least one author registers for the entirety of the workshop. We especially encourage participation from the Global South and underrepresented stakeholders in the dominant XAI discourse, striving for a more equitable conversation.

Preparing your Submission

For this year's edition, we have two types of papers: (a) research and (b) position papers. Research papers are intended to contain results (preliminary findings are fine) for empirical contributions to the field. Position papers, in turn, should ask provocative questions or provide future pathways for the HCXAI community.

Authors are invited to submit papers of up to 5 (FIVE) pages excluding references. Papers should be formatted in accordance with the single-column ACM SIGCHI format. Online guidance is available: https://www.acm.org/publications/authors/submissions. 
 

Templates are available for the following platforms: 

• Overleaf (Latex) (or search for ACM Conference Proceedings Primary Article)
• Microsoft Word
• LaTeX  (Use sample-manuscript.tex for submissions, and use \documentclass[manuscript, review]{acmart}.)

Reviewers will review the papers in the single-column format. Contact authors of accepted papers will receive instructions on how to prepare and submit a final version by the Publication-Ready Deadline. 

Submissions are single-blind reviewed; i.e., submissions must include the author’s names and affiliation. The workshop's organizing and program committees will review the submissions and accepted papers will be presented at the workshop. We ask that at least one of the authors of each accepted position paper attends the workshop. Presenting authors must register for the workshop and at least one full day of the conference.

Submissions must be original and relevant contributions to the workshop's theme. Each paper should directly and explicitly address how it speaks to the workshop's goals and themes. Pro-tip: direct mapping to a question or workshop goal posed will help. We are looking for papers that take a well-justified argument (for position papers) and/or empirically-backed studies (for research papers) and can generate productive and lively discussions during the workshop. Examples include, but not limited to, papers that include research summaries, literature reviews, industrial perspectives, real-world approaches, study results, or work-in-progress research projects. At the very least, submissions will be hosted on the website in line with what we have done for past years. For HCXAI 2025, the accepted works of HCXAI@CHI will likely be published in a dedicated workshop proceedings format including DOIs (more coming soon).
 
Submission pro tips:

1. Explicitly align your submission with the workshop's goals and topics. How? (a) Refer to the questions in the Call for Papers. (b) Read the workshop proposal

2. Engage with past submissions (build on, don't repeat). This year, we are putting extra emphasis on how authors are building on prior papers in this workshop. All papers are available on the website. Please engage with them, and build on them. 

3. Position papers must make a well-justified argument, not just summarize findings. This means that even if you are summarizing findings, make an argument around that summarization and justify why that argument (position) is something that is discussion-worthy and valuable to the community.
4. Research papers must provide well-articulated contributions, not just imagined studies. Preliminary studies and results are fine. Imagined/proposed studies are not. Research papers should outline a clear problem that is addressed by a study (or meta-analysis or reanalysis of previous studies). The contributions must be clear and well-situated in the literature. 

Workshop Topics and Guiding Questions: 

• How has the concept of explainability evolved in the era of large language models (LLMs)?
• Does traditional LLM benchmarking address the needs of XAI systems? If yes, how? If not, why?
• What XAI techniques can help users detect hallucinations in LLM outputs? How can XAI techniques help users calibrate their trust in LLM outputs?
• Considering different “whos,” how should XAI be utilized for Civic AI design for policymakers and governments?
• How can inappropriate explainability methods hinder our ability to detect hallucinations in AI models?
• What role should XAI play in promoting responsible AI practices in the context of LLMs?
• What are the best practices for auditing XAI systems, particularly those incorporating generative AI?
• Which participatory design techniques can be used to fine-tune LLMs to generate personalized explanations?
• How might seamful XAI design be leveraged to red-team and stress-test LLMs?
• What is the role of XAI in the field of AI audits, especially as regulatory landscapes evolve around government use of AI?
• In civic AI contexts, how could XAI help artists protect their work against AI plagiarism and support copyright disputes while ensuring that public cultural resources are respected?
• How might XAI systems empower gig workers and data workers and empower them to seek recourse in cases of disputes and promote accountability?
• How can we address specific XAI challenges faced by the Global South (Majority World) ensuring that these solutions are inclusive and culturally sensitive?

We aim to have global and diverse participation in the workshop given its hybrid (virtual-first) design format reduces visa or travel-related burdens,. With an effort towards equitable conversations, we welcome participation from under-represented perspectives and communities in XAI (e.g., lessons from the Global South, civil liberties and human rights perspectives, etc.)

Submit Paper (Easychair)